apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-12-24 13:28:13 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

Remove GPUMemoryChecker initialization

Browse Source 
Removed memory checker initialization from GPU model runner.
This commit is contained in:
Jiang-Jia-Jun
2025-12-16 11:09:27 +08:00
committed by GitHub
parent ff45ac078e
commit 075bd71272
1 changed files with 0 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
fastdeploy/worker/gpu_model_runner.py
View File

@@ -187,7 +187,6 @@ class GPUModelRunner(ModelRunnerBase):
self.cudagraph_capture_sizes = list(reversed(self.graph_opt_config.cudagraph_capture_sizes))
self.sot_warmup_sizes = self.graph_opt_config.sot_warmup_sizes
self.cudagraph_only_prefill = self.graph_opt_config.cudagraph_only_prefill
self.mem_checker = GPUMemoryChecker(device_id=self.device_id, print_debug_info=False)
# Initialize share inputs
self._init_share_inputs(self.scheduler_config.max_num_seqs)